Scientific Research and Essays

  • Abbreviation: Sci. Res. Essays
  • Language: English
  • ISSN: 1992-2248
  • DOI: 10.5897/SRE
  • Start Year: 2006
  • Published Articles: 2754

Full Length Research Paper

On the delay and link utilization with the new-additive increase multiplicative decrease congestion avoidance and control algorithm

  Hayder Natiq Jasem1,2*, Zuriati Ahmad Zukarnain1, Mohamed Othman1 and       Shamala Subramaniam1
    1Department of Communication Technology and Networks, Faculty of Computer Science and Information Technology, University Putra Malaysia. 2Department of Computer Science, Faculty of Science for Woman, University of Baghdad, Iraq.  
Email: [email protected]

  •  Accepted: 15 November 2010
  •  Published: 31 December 2010




Additive increase multiplicative decrease (AIMD) algorithm is the prevailing algorithm for congestion avoidance and control in the Internet. Reducing the end-to-end delays and enhancement of the link utilization are the important goals of this algorithm. In this work, we continue to study the performance of the New-AIMD (additive increase multiplicative decrease) mechanism as one of the core protocols for TCP, to avoid and control the congestion. We want to evaluate the effect of using the AIMD algorithm after developing it, which we called the New-AIMD algorithm, to find a new approach to measure the end-to-end delay and bottleneck link utilization and use the NCTUns simulator to obtain the results after making the modification for the mechanism. We will use the DropTail mechanism as the active queue management mechanism (AQM) in the bottleneck router. After the implementation of our new approach with a different number of flows, we expect the end-to-end delay to be less when we measure the delay dependent on the throughput for the entire system. In addition, we will measure the bottleneck link utilization using this mechanism and expect to get high utilization for bottleneck link and avoid the collisions in the link.


Key words: Congestion control, TCP, AIMD, delay, link utilization.